Vision Transformer (ViT)
A Vision Transformer cuts a picture into small squares and checks how the squares relate to each other.
What it does
A Vision Transformer cuts a picture into small squares and checks how the squares relate to each other.
Patch: A small square of a photo • Attention: Focusing on what matters
How it works
- Cut the image into patches.
- Treat each patch like a word in a sentence.
- Use attention to connect the patches that matter.
Uses & Applications
- A photo app can understand a whole scene, not just one corner.
- A medical tool can compare areas of a scan.
- A satellite tool can study land, roads, or buildings in large images.
In short
It treats an image like a puzzle to understand the big picture.
Try it yourself
Let picture pieces share clues
Cut a picture into sixteen patches. One patch looks at the others to decide which clues to mix together.
Your turn
Change one setting at a time. Reset example puts everything back.
Relate image patches
Step 1Why this happens